Struct ConversationChain 

pub struct ConversationChain { /* private fields */ }

Conversation Chain

A Chain with memory that automatically saves and loads conversation history.

Implementations

impl ConversationChain

pub fn new<L>(llm: L, memory: ConversationBufferMemory) -> Self

where L: BaseChatModel + Send + Sync + 'static, L::Error: Into<ProviderError>,

Create a new ConversationChain.

Arguments

• llm - LLM client (any type implementing BaseChatModel)
• memory - Conversation memory

pub fn from_memory<L>(llm: L, memory: Arc<Mutex<dyn BaseMemory>>) -> Self

where L: BaseChatModel + Send + Sync + 'static, L::Error: Into<ProviderError>,

Create a ConversationChain from any BaseMemory implementation.

Unlike ConversationChain::new (which takes the concrete ConversationBufferMemory), this accepts any memory — window, summary, vector-store, persistent — so the chain’s memory is pluggable without changing the chain source.

pub fn with_system_prompt(self, prompt: impl Into<String>) -> Self

Set system prompt.

pub fn with_input_key(self, key: impl Into<String>) -> Self

Set input key name.

pub fn with_output_key(self, key: impl Into<String>) -> Self

Set output key name.

pub fn with_name(self, name: impl Into<String>) -> Self

Set chain name.

pub fn with_verbose(self, verbose: bool) -> Self

Set verbose mode.

pub fn memory(&self) -> &Arc<Mutex<dyn BaseMemory>>

Get memory reference.

pub fn builder<L>(llm: L) -> ConversationChainBuilder

where L: BaseChatModel + Send + Sync + 'static, L::Error: Into<ProviderError>,

Create a ConversationChainBuilder from an LLM.

pub async fn clear_memory(&self) -> Result<(), ChainError>

Clear memory.

pub async fn predict( &self, input: impl Into<String>, ) -> Result<String, ChainError>

Simplified prediction interface.

Takes a user input string, returns AI response string.

pub fn prepare_messages( &self, input: &str, history_messages: &[Message], ) -> Vec<Message>

Prepare message list.

Combines system prompt, history messages, and current user input.

Trait Implementations

impl BaseChain for ConversationChain

fn stream<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, ) -> Pin<Box<dyn Future<Output = Result<ChainStream, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream execution for ConversationChain – token by token output.

fn input_keys(&self) -> Vec<&str>

Get input keys.

fn output_keys(&self) -> Vec<&str>

Get output keys.

fn invoke<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, ) -> Pin<Box<dyn Future<Output = Result<ChainResult, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Execute the Chain.

fn name(&self) -> &str

Get Chain name.

fn invoke_with_config<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<ChainResult, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Execute the Chain with a RunnableConfig.

fn stream_with_config<'life0, 'async_trait>( &'life0 self, inputs: HashMap<String, Value>, config: Option<RunnableConfig>, ) -> Pin<Box<dyn Future<Output = Result<ChainStream, ChainError>> + Send + 'async_trait>>

where Self: 'async_trait, 'life0: 'async_trait,

Stream execute the Chain with a RunnableConfig.

fn validate_inputs( &self, inputs: &HashMap<String, Value>, ) -> Result<(), ChainError>

Validate inputs.